{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UXRRZON26ZVLLOEVPZZNT2HBTD","short_pith_number":"pith:UXRRZON2","canonical_record":{"source":{"id":"2112.10728","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-20T18:23:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f828145f48353ac9b532f68c0c469e456f5ee8965fa94528bc644193eadb46ef","abstract_canon_sha256":"3e2b4f72b83e33326d20d81825c1fd1220d7b49af7a9e8afec03fcab89847b45"},"schema_version":"1.0"},"canonical_sha256":"a5e31cb9baf66ab5b8957e72d9e8e198eaf8d314f6d85feed6f6703c7e757e5b","source":{"kind":"arxiv","id":"2112.10728","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10728","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10728v2","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10728","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"UXRRZON26ZVL","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"UXRRZON26ZVLLOEV","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"UXRRZON2","created_at":"2026-07-05T04:20:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UXRRZON26ZVLLOEVPZZNT2HBTD","target":"record","payload":{"canonical_record":{"source":{"id":"2112.10728","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-20T18:23:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f828145f48353ac9b532f68c0c469e456f5ee8965fa94528bc644193eadb46ef","abstract_canon_sha256":"3e2b4f72b83e33326d20d81825c1fd1220d7b49af7a9e8afec03fcab89847b45"},"schema_version":"1.0"},"canonical_sha256":"a5e31cb9baf66ab5b8957e72d9e8e198eaf8d314f6d85feed6f6703c7e757e5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:17.709081Z","signature_b64":"YZ+LSSeK57AII85lgdJcG6VQ0vpFRaeWQfAGjlV58qh0oqHzd4afN0MHbVu3TYrLnvAyW99V8QMcm/+bNHjJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5e31cb9baf66ab5b8957e72d9e8e198eaf8d314f6d85feed6f6703c7e757e5b","last_reissued_at":"2026-07-05T04:20:17.708572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:17.708572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.10728","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ebN24nA9jh1XR9tXMrnPcRlwGUV7fuvT7iNQVruhcJJpkPXWZE17rx1+VQmTgz9p3u9My1QurplyvwP89NqYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:56:10.888986Z"},"content_sha256":"72a90a0d11603f65432b95a4fe99d4427f7a7047d3e7ceef1178b6ab16a244e0","schema_version":"1.0","event_id":"sha256:72a90a0d11603f65432b95a4fe99d4427f7a7047d3e7ceef1178b6ab16a244e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UXRRZON26ZVLLOEVPZZNT2HBTD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alexander Schwing, Avirup Sil, Haoyang Wen, Heng Ji, Jaemin Cho, Lifu Huang, Manling Li, Mohit Bansal, Revanth Gangi Reddy, Shih-Fu Chang, Xilin Rui, Xudong Lin","submitted_at":"2021-12-20T18:23:30Z","abstract_excerpt":"Recently, there has been an increasing interest in building question answering (QA) models that reason across multiple modalities, such as text and images. However, QA using images is often limited to just picking the answer from a pre-defined set of options. In addition, images in the real world, especially in news, have objects that are co-referential to the text, with complementary information from both modalities. In this paper, we present a new QA evaluation benchmark with 1,384 questions over news articles that require cross-media grounding of objects in images onto text. Specifically, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10728","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.10728/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D6ryck/BXEOP81WY76HXodH6OXFlRnTnxSO+DypJ9vMCzyM1qzMWvU0N64AVe/WhD/7SXMh5lHbBbjouq7jMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:56:10.889521Z"},"content_sha256":"a3b01f8589a4b6c26b331e22caebca931f7bad10a826132426ae41107c3eabd4","schema_version":"1.0","event_id":"sha256:a3b01f8589a4b6c26b331e22caebca931f7bad10a826132426ae41107c3eabd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UXRRZON26ZVLLOEVPZZNT2HBTD/bundle.json","state_url":"https://pith.science/pith/UXRRZON26ZVLLOEVPZZNT2HBTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UXRRZON26ZVLLOEVPZZNT2HBTD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T14:56:10Z","links":{"resolver":"https://pith.science/pith/UXRRZON26ZVLLOEVPZZNT2HBTD","bundle":"https://pith.science/pith/UXRRZON26ZVLLOEVPZZNT2HBTD/bundle.json","state":"https://pith.science/pith/UXRRZON26ZVLLOEVPZZNT2HBTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UXRRZON26ZVLLOEVPZZNT2HBTD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UXRRZON26ZVLLOEVPZZNT2HBTD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3e2b4f72b83e33326d20d81825c1fd1220d7b49af7a9e8afec03fcab89847b45","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-20T18:23:30Z","title_canon_sha256":"f828145f48353ac9b532f68c0c469e456f5ee8965fa94528bc644193eadb46ef"},"schema_version":"1.0","source":{"id":"2112.10728","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10728","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10728v2","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10728","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_12","alias_value":"UXRRZON26ZVL","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_16","alias_value":"UXRRZON26ZVLLOEV","created_at":"2026-07-05T04:20:17Z"},{"alias_kind":"pith_short_8","alias_value":"UXRRZON2","created_at":"2026-07-05T04:20:17Z"}],"graph_snapshots":[{"event_id":"sha256:a3b01f8589a4b6c26b331e22caebca931f7bad10a826132426ae41107c3eabd4","target":"graph","created_at":"2026-07-05T04:20:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.10728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been an increasing interest in building question answering (QA) models that reason across multiple modalities, such as text and images. However, QA using images is often limited to just picking the answer from a pre-defined set of options. In addition, images in the real world, especially in news, have objects that are co-referential to the text, with complementary information from both modalities. In this paper, we present a new QA evaluation benchmark with 1,384 questions over news articles that require cross-media grounding of objects in images onto text. Specifically, t","authors_text":"Alexander Schwing, Avirup Sil, Haoyang Wen, Heng Ji, Jaemin Cho, Lifu Huang, Manling Li, Mohit Bansal, Revanth Gangi Reddy, Shih-Fu Chang, Xilin Rui, Xudong Lin","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-20T18:23:30Z","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10728","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:72a90a0d11603f65432b95a4fe99d4427f7a7047d3e7ceef1178b6ab16a244e0","target":"record","created_at":"2026-07-05T04:20:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3e2b4f72b83e33326d20d81825c1fd1220d7b49af7a9e8afec03fcab89847b45","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-20T18:23:30Z","title_canon_sha256":"f828145f48353ac9b532f68c0c469e456f5ee8965fa94528bc644193eadb46ef"},"schema_version":"1.0","source":{"id":"2112.10728","kind":"arxiv","version":2}},"canonical_sha256":"a5e31cb9baf66ab5b8957e72d9e8e198eaf8d314f6d85feed6f6703c7e757e5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5e31cb9baf66ab5b8957e72d9e8e198eaf8d314f6d85feed6f6703c7e757e5b","first_computed_at":"2026-07-05T04:20:17.708572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:17.708572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YZ+LSSeK57AII85lgdJcG6VQ0vpFRaeWQfAGjlV58qh0oqHzd4afN0MHbVu3TYrLnvAyW99V8QMcm/+bNHjJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:17.709081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.10728","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72a90a0d11603f65432b95a4fe99d4427f7a7047d3e7ceef1178b6ab16a244e0","sha256:a3b01f8589a4b6c26b331e22caebca931f7bad10a826132426ae41107c3eabd4"],"state_sha256":"fb92ce015c04edb76afbe71406d1c77266dd6658281b5cff16e1e40d0651615f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5RY0To6jLwd81NqzWkrZCozD+U+UfFVFzrICZ6oBpAJGVhqyxWel9fYaT+XUUSHo72uUZ+yF3P/4ZYjW7nzWAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:56:10.893187Z","bundle_sha256":"4ca0a96e1be16f301d74337eae6ae3e5e85dde7c087bd7b4c0a00a02190baedf"}}